[ICLR 2024 (Spotlight)] "Frozen Transformers in Language Models are Effective Visual Encoder Layers"

Linux命令大全搜索工具，内容包含Linux命令手册、详解、学习、搜集。https://git.io/linux

✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Build Text Rerankers with Deep Language Models

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.

基于大语言模型的检索增强生成RAG示例

Sample GLM4V + ChatTTS AI assistant

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Scrape company overview information and reviews from Glassdoor using a proxy network and SQLite database.

Guideline following Large Language Model for Information Extraction

Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。

A web-scraping-based python package that enables you to scrape data from various platforms like GitHub, Twitter, Instagram, or any useful website.

润学全球官方指定GITHUB，整理润学宗旨、纲领、理论和各类润之实例；解决为什么润，润去哪里，怎么润三大问题； 并成为新中国人的核心宗教，核心信念。

基于pytorch的GlobalPointer进行中文命名实体识别。

基于pytorch使用自己的数据继续训练bert

中文信息抽取，包含实体抽取、关系抽取、事件抽取

利用指针网络进行信息抽取，包含命名实体识别、关系抽取、事件抽取。

The datasets for image emotion computing

Implementation of "Joint Image Emotion Classification and Distribution Learning via Deep Convolutional Neural Network"

sketch + style = paints 🎨 (TOG2018/SIGGRAPH2018ASIA)

开屏跳过-安卓系统的开屏广告自动跳过助手

一个没什么用的VSC插件

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Chinese version of GPT2 training code, using BERT tokenizer.

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

基于GPT2的中文摘要生成模型

中文生成式预训练模型